Intel OpenFL - RuntimeError: mat1 and mat2 shapes cannot be multiplied (128x512 and 2048x4096)
Intel OpenFL - RuntimeError: mat1 and mat2 shapes cannot be multiplied (128x512 and 2048x4096)
我正在尝试 运行 我的笔记本（在 google colab 或其他类似平台上运行良好）在 Intel OpenFL 上，Intel 的 FL 新框架。
我正在使用 MNIST 进行此转换：
trf = transforms.Compose(
[transforms.Resize(32),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
])
这是我的网：
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
# calculate same padding:
# (w - k + 2*p)/s + 1 = o
# => p = (s(o-1) - w + k)/2
self.block_1 = nn.Sequential(
nn.Conv2d(in_channels=1,
out_channels=64,
kernel_size=(3, 3),
stride=(1, 1),
# (1(32-1)- 32 + 3)/2 = 1
padding=1),
nn.BatchNorm2d(64),
nn.ReLU(),
nn.Conv2d(in_channels=64,
out_channels=64,
kernel_size=(3, 3),
stride=(1, 1),
padding=1),
nn.BatchNorm2d(64),
nn.ReLU(),
nn.MaxPool2d(kernel_size=(2, 2),
stride=(2, 2))
)
self.block_2 = nn.Sequential(
nn.Conv2d(in_channels=64,
out_channels=128,
kernel_size=(3, 3),
stride=(1, 1),
padding=1),
nn.BatchNorm2d(128),
nn.ReLU(),
nn.Conv2d(in_channels=128,
out_channels=128,
kernel_size=(3, 3),
stride=(1, 1),
padding=1),
nn.BatchNorm2d(128),
nn.ReLU(),
nn.MaxPool2d(kernel_size=(2, 2),
stride=(2, 2))
)
self.block_3 = nn.Sequential(
nn.Conv2d(in_channels=128,
out_channels=256,
kernel_size=(3, 3),
stride=(1, 1),
padding=1),
nn.BatchNorm2d(256),
nn.ReLU(),
nn.Conv2d(in_channels=256,
out_channels=256,
kernel_size=(3, 3),
stride=(1, 1),
padding=1),
nn.BatchNorm2d(256),
nn.ReLU(),
nn.Conv2d(in_channels=256,
out_channels=256,
kernel_size=(3, 3),
stride=(1, 1),
padding=1),
nn.BatchNorm2d(256),
nn.ReLU(),
nn.MaxPool2d(kernel_size=(2, 2),
stride=(2, 2))
)
self.block_4 = nn.Sequential(
nn.Conv2d(in_channels=256,
out_channels=512,
kernel_size=(3, 3),
stride=(1, 1),
padding=1),
nn.BatchNorm2d(512),
nn.ReLU(),
nn.Conv2d(in_channels=512,
out_channels=512,
kernel_size=(3, 3),
stride=(1, 1),
padding=1),
nn.BatchNorm2d(512),
nn.ReLU(),
nn.Conv2d(in_channels=512,
out_channels=512,
kernel_size=(3, 3),
stride=(1, 1),
padding=1),
nn.BatchNorm2d(512),
nn.ReLU(),
nn.MaxPool2d(kernel_size=(2, 2),
stride=(2, 2))
)
self.classifier = nn.Sequential(
nn.Linear(2048, 4096),
nn.ReLU(True),
nn.Dropout(p=0.65),
nn.Linear(4096, 4096),
nn.ReLU(True),
nn.Dropout(p=0.65),
nn.Linear(4096, classes)
)
for m in self.modules():
if isinstance(m, torch.nn.Conv2d) or isinstance(m, torch.nn.Linear):
nn.init.kaiming_uniform_(m.weight, mode='fan_in', nonlinearity='leaky_relu')
# nn.init.xavier_normal_(m.weight)
if m.bias is not None:
m.bias.detach().zero_()
# self.avgpool = nn.AdaptiveAvgPool2d((7, 7))
def forward(self, x):
x = self.block_1(x)
x = self.block_2(x)
x = self.block_3(x)
x = self.block_4(x)
# x = self.avgpool(x)
x = x.view(x.size(0), -1)
x = self.classifier(x)
return x
但是我有这个错误：
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
/var/folders/pm/nj7yy3px76n6b62knyrn8r_40000gn/T/ipykernel_10337/666012611.py in <module>
----> 1 final_model = fx.run_experiment(collaborators,{'aggregator.settings.rounds_to_train':5})
/opt/anaconda3/envs/my_env/lib/python3.7/site-packages/openfl/native/native.py in run_experiment(collaborator_dict, override_config)
282 for col in plan.authorized_cols:
283 collaborator = collaborators[col]
--> 284 collaborator.run_simulation()
285
286 # Set the weights for the final model
/opt/anaconda3/envs/my_env/lib/python3.7/site-packages/openfl/component/collaborator/collaborator.py in run_simulation(self)
170 self.logger.info(f'Received the following tasks: {tasks}')
171 for task in tasks:
--> 172 self.do_task(task, round_number)
173 self.logger.info(f'All tasks completed on {self.collaborator_name} '
174 f'for round {round_number}...')
/opt/anaconda3/envs/my_env/lib/python3.7/site-packages/openfl/component/collaborator/collaborator.py in do_task(self, task, round_number)
245 round_num=round_number,
246 input_tensor_dict=input_tensor_dict,
--> 247 **kwargs)
248
249 # Save global and local output_tensor_dicts to TensorDB
/opt/anaconda3/envs/my_env/lib/python3.7/site-packages/openfl/federated/task/runner_pt.py in validate(self, col_name, round_num, input_tensor_dict, use_tqdm, **kwargs)
106 data, target = pt.tensor(data).to(self.device), pt.tensor(
107 target).to(self.device, dtype=pt.int64)
--> 108 output = self(data)
109 # get the index of the max log-probability
110 pred = output.argmax(dim=1, keepdim=True)
/opt/anaconda3/envs/my_env/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
887 result = self._slow_forward(*input, **kwargs)
888 else:
--> 889 result = self.forward(*input, **kwargs)
890 for hook in itertools.chain(
891 _global_forward_hooks.values(),
/var/folders/pm/nj7yy3px76n6b62knyrn8r_40000gn/T/ipykernel_10337/3611293808.py in forward(self, x)
125 # x = self.avgpool(x)
126 x = x.view(x.size(0), -1)
--> 127 x = self.classifier(x)
128 return x
/opt/anaconda3/envs/my_env/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
887 result = self._slow_forward(*input, **kwargs)
888 else:
--> 889 result = self.forward(*input, **kwargs)
890 for hook in itertools.chain(
891 _global_forward_hooks.values(),
/opt/anaconda3/envs/my_env/lib/python3.7/site-packages/torch/nn/modules/container.py in forward(self, input)
117 def forward(self, input):
118 for module in self:
--> 119 input = module(input)
120 return input
121
/opt/anaconda3/envs/my_env/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
887 result = self._slow_forward(*input, **kwargs)
888 else:
--> 889 result = self.forward(*input, **kwargs)
890 for hook in itertools.chain(
891 _global_forward_hooks.values(),
/opt/anaconda3/envs/my_env/lib/python3.7/site-packages/torch/nn/modules/linear.py in forward(self, input)
92
93 def forward(self, input: Tensor) -> Tensor:
---> 94 return F.linear(input, self.weight, self.bias)
95
96 def extra_repr(self) -> str:
/opt/anaconda3/envs/my_env/lib/python3.7/site-packages/torch/nn/functional.py in linear(input, weight, bias)
1751 if has_torch_function_variadic(input, weight):
1752 return handle_torch_function(linear, (input, weight), input, weight, bias=bias)
-> 1753 return torch._C._nn.linear(input, weight, bias)
1754
1755
RuntimeError: mat1 and mat2 shapes cannot be multiplied (128x512 and 2048x4096)
但是，完全相同的网络在 Google Colab 上运行良好。可能我遗漏了一些关于 OpenFL 的东西。
这是我的问题：我使用的是 28x28 图像，而这个网络使用 32x32 图像
我正在尝试 运行 我的笔记本（在 google colab 或其他类似平台上运行良好）在 Intel OpenFL 上，Intel 的 FL 新框架。 我正在使用 MNIST 进行此转换：
trf = transforms.Compose(
[transforms.Resize(32),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
])
这是我的网：
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
# calculate same padding:
# (w - k + 2*p)/s + 1 = o
# => p = (s(o-1) - w + k)/2
self.block_1 = nn.Sequential(
nn.Conv2d(in_channels=1,
out_channels=64,
kernel_size=(3, 3),
stride=(1, 1),
# (1(32-1)- 32 + 3)/2 = 1
padding=1),
nn.BatchNorm2d(64),
nn.ReLU(),
nn.Conv2d(in_channels=64,
out_channels=64,
kernel_size=(3, 3),
stride=(1, 1),
padding=1),
nn.BatchNorm2d(64),
nn.ReLU(),
nn.MaxPool2d(kernel_size=(2, 2),
stride=(2, 2))
)
self.block_2 = nn.Sequential(
nn.Conv2d(in_channels=64,
out_channels=128,
kernel_size=(3, 3),
stride=(1, 1),
padding=1),
nn.BatchNorm2d(128),
nn.ReLU(),
nn.Conv2d(in_channels=128,
out_channels=128,
kernel_size=(3, 3),
stride=(1, 1),
padding=1),
nn.BatchNorm2d(128),
nn.ReLU(),
nn.MaxPool2d(kernel_size=(2, 2),
stride=(2, 2))
)
self.block_3 = nn.Sequential(
nn.Conv2d(in_channels=128,
out_channels=256,
kernel_size=(3, 3),
stride=(1, 1),
padding=1),
nn.BatchNorm2d(256),
nn.ReLU(),
nn.Conv2d(in_channels=256,
out_channels=256,
kernel_size=(3, 3),
stride=(1, 1),
padding=1),
nn.BatchNorm2d(256),
nn.ReLU(),
nn.Conv2d(in_channels=256,
out_channels=256,
kernel_size=(3, 3),
stride=(1, 1),
padding=1),
nn.BatchNorm2d(256),
nn.ReLU(),
nn.MaxPool2d(kernel_size=(2, 2),
stride=(2, 2))
)
self.block_4 = nn.Sequential(
nn.Conv2d(in_channels=256,
out_channels=512,
kernel_size=(3, 3),
stride=(1, 1),
padding=1),
nn.BatchNorm2d(512),
nn.ReLU(),
nn.Conv2d(in_channels=512,
out_channels=512,
kernel_size=(3, 3),
stride=(1, 1),
padding=1),
nn.BatchNorm2d(512),
nn.ReLU(),
nn.Conv2d(in_channels=512,
out_channels=512,
kernel_size=(3, 3),
stride=(1, 1),
padding=1),
nn.BatchNorm2d(512),
nn.ReLU(),
nn.MaxPool2d(kernel_size=(2, 2),
stride=(2, 2))
)
self.classifier = nn.Sequential(
nn.Linear(2048, 4096),
nn.ReLU(True),
nn.Dropout(p=0.65),
nn.Linear(4096, 4096),
nn.ReLU(True),
nn.Dropout(p=0.65),
nn.Linear(4096, classes)
)
for m in self.modules():
if isinstance(m, torch.nn.Conv2d) or isinstance(m, torch.nn.Linear):
nn.init.kaiming_uniform_(m.weight, mode='fan_in', nonlinearity='leaky_relu')
# nn.init.xavier_normal_(m.weight)
if m.bias is not None:
m.bias.detach().zero_()
# self.avgpool = nn.AdaptiveAvgPool2d((7, 7))
def forward(self, x):
x = self.block_1(x)
x = self.block_2(x)
x = self.block_3(x)
x = self.block_4(x)
# x = self.avgpool(x)
x = x.view(x.size(0), -1)
x = self.classifier(x)
return x
但是我有这个错误：
---------------------------------------------------------------------------
RuntimeError Traceback (most recent call last)
/var/folders/pm/nj7yy3px76n6b62knyrn8r_40000gn/T/ipykernel_10337/666012611.py in <module>
----> 1 final_model = fx.run_experiment(collaborators,{'aggregator.settings.rounds_to_train':5})
/opt/anaconda3/envs/my_env/lib/python3.7/site-packages/openfl/native/native.py in run_experiment(collaborator_dict, override_config)
282 for col in plan.authorized_cols:
283 collaborator = collaborators[col]
--> 284 collaborator.run_simulation()
285
286 # Set the weights for the final model
/opt/anaconda3/envs/my_env/lib/python3.7/site-packages/openfl/component/collaborator/collaborator.py in run_simulation(self)
170 self.logger.info(f'Received the following tasks: {tasks}')
171 for task in tasks:
--> 172 self.do_task(task, round_number)
173 self.logger.info(f'All tasks completed on {self.collaborator_name} '
174 f'for round {round_number}...')
/opt/anaconda3/envs/my_env/lib/python3.7/site-packages/openfl/component/collaborator/collaborator.py in do_task(self, task, round_number)
245 round_num=round_number,
246 input_tensor_dict=input_tensor_dict,
--> 247 **kwargs)
248
249 # Save global and local output_tensor_dicts to TensorDB
/opt/anaconda3/envs/my_env/lib/python3.7/site-packages/openfl/federated/task/runner_pt.py in validate(self, col_name, round_num, input_tensor_dict, use_tqdm, **kwargs)
106 data, target = pt.tensor(data).to(self.device), pt.tensor(
107 target).to(self.device, dtype=pt.int64)
--> 108 output = self(data)
109 # get the index of the max log-probability
110 pred = output.argmax(dim=1, keepdim=True)
/opt/anaconda3/envs/my_env/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
887 result = self._slow_forward(*input, **kwargs)
888 else:
--> 889 result = self.forward(*input, **kwargs)
890 for hook in itertools.chain(
891 _global_forward_hooks.values(),
/var/folders/pm/nj7yy3px76n6b62knyrn8r_40000gn/T/ipykernel_10337/3611293808.py in forward(self, x)
125 # x = self.avgpool(x)
126 x = x.view(x.size(0), -1)
--> 127 x = self.classifier(x)
128 return x
/opt/anaconda3/envs/my_env/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
887 result = self._slow_forward(*input, **kwargs)
888 else:
--> 889 result = self.forward(*input, **kwargs)
890 for hook in itertools.chain(
891 _global_forward_hooks.values(),
/opt/anaconda3/envs/my_env/lib/python3.7/site-packages/torch/nn/modules/container.py in forward(self, input)
117 def forward(self, input):
118 for module in self:
--> 119 input = module(input)
120 return input
121
/opt/anaconda3/envs/my_env/lib/python3.7/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
887 result = self._slow_forward(*input, **kwargs)
888 else:
--> 889 result = self.forward(*input, **kwargs)
890 for hook in itertools.chain(
891 _global_forward_hooks.values(),
/opt/anaconda3/envs/my_env/lib/python3.7/site-packages/torch/nn/modules/linear.py in forward(self, input)
92
93 def forward(self, input: Tensor) -> Tensor:
---> 94 return F.linear(input, self.weight, self.bias)
95
96 def extra_repr(self) -> str:
/opt/anaconda3/envs/my_env/lib/python3.7/site-packages/torch/nn/functional.py in linear(input, weight, bias)
1751 if has_torch_function_variadic(input, weight):
1752 return handle_torch_function(linear, (input, weight), input, weight, bias=bias)
-> 1753 return torch._C._nn.linear(input, weight, bias)
1754
1755
RuntimeError: mat1 and mat2 shapes cannot be multiplied (128x512 and 2048x4096)
但是，完全相同的网络在 Google Colab 上运行良好。可能我遗漏了一些关于 OpenFL 的东西。
这是我的问题：我使用的是 28x28 图像，而这个网络使用 32x32 图像